Exemplo n.º 1
0
            "*****@*****.**",
            "*****@*****.**",
            "*****@*****.**",
        ],
        date_partition_parameter="submission_date",
        depends_on_past=False,
        dag=dag,
    )

    search_derived__search_aggregates__v8.set_upstream(
        search_derived__search_clients_daily__v8)

    wait_for_telemetry_derived__clients_daily_joined__v1 = ExternalTaskCompletedSensor(
        task_id="wait_for_telemetry_derived__clients_daily_joined__v1",
        external_dag_id="bqetl_main_summary",
        external_task_id="telemetry_derived__clients_daily_joined__v1",
        execution_delta=datetime.timedelta(seconds=3600),
        check_existence=True,
        mode="reschedule",
        pool="DATA_ENG_EXTERNALTASKSENSOR",
    )

    search_derived__search_clients_daily__v8.set_upstream(
        wait_for_telemetry_derived__clients_daily_joined__v1)

    search_derived__search_clients_last_seen__v1.set_upstream(
        search_derived__search_clients_daily__v8)

    search_derived__search_metric_contribution__v1.set_upstream(
        search_derived__search_clients_daily__v8)
Exemplo n.º 2
0
        task_id="telemetry_derived__smoot_usage_nondesktop_compressed__v2",
        destination_table="smoot_usage_nondesktop_compressed_v2",
        dataset_id="telemetry_derived",
        project_id="moz-fx-data-shared-prod",
        owner="*****@*****.**",
        email=["*****@*****.**", "*****@*****.**"],
        date_partition_parameter="submission_date",
        depends_on_past=False,
        dag=dag,
    )

    wait_for_telemetry_derived__clients_last_seen__v1 = ExternalTaskCompletedSensor(
        task_id="wait_for_telemetry_derived__clients_last_seen__v1",
        external_dag_id="bqetl_main_summary",
        external_task_id="telemetry_derived__clients_last_seen__v1",
        execution_delta=datetime.timedelta(seconds=3600),
        check_existence=True,
        mode="reschedule",
        pool="DATA_ENG_EXTERNALTASKSENSOR",
    )

    telemetry_derived__smoot_usage_desktop__v2.set_upstream(
        wait_for_telemetry_derived__clients_last_seen__v1
    )

    telemetry_derived__smoot_usage_desktop_compressed__v2.set_upstream(
        telemetry_derived__smoot_usage_desktop__v2
    )

    wait_for_firefox_accounts_derived__fxa_users_last_seen__v1 = (
        ExternalTaskCompletedSensor(
        task_id="monitoring_derived__telemetry_missing_columns__v3",
        destination_table="telemetry_missing_columns_v3",
        dataset_id="monitoring_derived",
        project_id="moz-fx-data-shared-prod",
        owner="*****@*****.**",
        email=["*****@*****.**", "*****@*****.**"],
        date_partition_parameter="submission_date",
        depends_on_past=False,
        dag=dag,
    )

    wait_for_copy_deduplicate_all = ExternalTaskCompletedSensor(
        task_id="wait_for_copy_deduplicate_all",
        external_dag_id="copy_deduplicate",
        external_task_id="copy_deduplicate_all",
        execution_delta=datetime.timedelta(seconds=3600),
        check_existence=True,
        mode="reschedule",
        pool="DATA_ENG_EXTERNALTASKSENSOR",
    )

    monitoring_derived__average_ping_sizes__v1.set_upstream(
        wait_for_copy_deduplicate_all
    )

    monitoring_derived__average_ping_sizes__v1.set_upstream(
        monitoring_derived__stable_table_sizes__v1
    )

    wait_for_copy_deduplicate_main_ping = ExternalTaskCompletedSensor(
        task_id="wait_for_copy_deduplicate_main_ping",
            "*****@*****.**",
        ],
        date_partition_parameter="submission_date",
        depends_on_past=False,
        dag=dag,
    )

    experiment_enrollment_daily_active_population.set_upstream(
        telemetry_derived__experiments_daily_active_clients__v1
    )

    wait_for_bq_main_events = ExternalTaskCompletedSensor(
        task_id="wait_for_bq_main_events",
        external_dag_id="copy_deduplicate",
        external_task_id="bq_main_events",
        execution_delta=datetime.timedelta(seconds=7200),
        check_existence=True,
        mode="reschedule",
        pool="DATA_ENG_EXTERNALTASKSENSOR",
    )

    telemetry_derived__experiment_enrollment_aggregates__v1.set_upstream(
        wait_for_bq_main_events
    )
    wait_for_copy_deduplicate_all = ExternalTaskCompletedSensor(
        task_id="wait_for_copy_deduplicate_all",
        external_dag_id="copy_deduplicate",
        external_task_id="copy_deduplicate_all",
        execution_delta=datetime.timedelta(seconds=7200),
        check_existence=True,
        mode="reschedule",
Exemplo n.º 5
0
    mozilla_vpn_derived__site_metrics_summary__v1 = bigquery_etl_query(
        task_id="mozilla_vpn_derived__site_metrics_summary__v1",
        destination_table="site_metrics_summary_v1",
        dataset_id="mozilla_vpn_derived",
        project_id="moz-fx-data-shared-prod",
        owner="*****@*****.**",
        email=["*****@*****.**", "*****@*****.**"],
        date_partition_parameter="date",
        depends_on_past=False,
        dag=dag,
    )

    wait_for_mozilla_vpn_derived__all_subscriptions__v1 = ExternalTaskCompletedSensor(
        task_id="wait_for_mozilla_vpn_derived__all_subscriptions__v1",
        external_dag_id="bqetl_subplat",
        external_task_id="mozilla_vpn_derived__all_subscriptions__v1",
        execution_delta=datetime.timedelta(seconds=47700),
        check_existence=True,
        mode="reschedule",
        pool="DATA_ENG_EXTERNALTASKSENSOR",
    )

    mozilla_vpn_derived__funnel_ga_to_subscriptions__v1.set_upstream(
        wait_for_mozilla_vpn_derived__all_subscriptions__v1)

    mozilla_vpn_derived__funnel_ga_to_subscriptions__v1.set_upstream(
        mozilla_vpn_derived__site_metrics_summary__v1)

    mozilla_vpn_derived__site_metrics_summary__v1.set_upstream(
        mozilla_vpn_derived__site_metrics_empty_check__v1)
Exemplo n.º 6
0
        destination_table="event_aggregates_v1",
        dataset_id="contextual_services_derived",
        project_id="moz-fx-data-shared-prod",
        owner="*****@*****.**",
        email=["*****@*****.**", "*****@*****.**"],
        date_partition_parameter="submission_date",
        depends_on_past=False,
        arguments=["--schema_update_option=ALLOW_FIELD_ADDITION"],
        dag=dag,
    )

    wait_for_copy_deduplicate_all = ExternalTaskCompletedSensor(
        task_id="wait_for_copy_deduplicate_all",
        external_dag_id="copy_deduplicate",
        external_task_id="copy_deduplicate_all",
        execution_delta=datetime.timedelta(seconds=7200),
        check_existence=True,
        mode="reschedule",
        pool="DATA_ENG_EXTERNALTASKSENSOR",
    )

    contextual_services_derived__event_aggregates__v1.set_upstream(
        wait_for_copy_deduplicate_all)
    wait_for_search_terms_derived__suggest_impression_sanitized__v1 = (
        ExternalTaskCompletedSensor(
            task_id=
            "wait_for_search_terms_derived__suggest_impression_sanitized__v1",
            external_dag_id="bqetl_search_terms_daily",
            external_task_id=
            "search_terms_derived__suggest_impression_sanitized__v1",
            check_existence=True,
Exemplo n.º 7
0
        destination_table="core_clients_last_seen_v1",
        dataset_id="telemetry_derived",
        project_id="moz-fx-data-shared-prod",
        owner="*****@*****.**",
        email=["*****@*****.**", "*****@*****.**"],
        date_partition_parameter="submission_date",
        depends_on_past=True,
        priority_weight=70,
        dag=dag,
    )

    wait_for_copy_deduplicate_all = ExternalTaskCompletedSensor(
        task_id="wait_for_copy_deduplicate_all",
        external_dag_id="copy_deduplicate",
        external_task_id="copy_deduplicate_all",
        execution_delta=datetime.timedelta(seconds=3600),
        check_existence=True,
        mode="reschedule",
        pool="DATA_ENG_EXTERNALTASKSENSOR",
    )

    telemetry_derived__core_clients_daily__v1.set_upstream(
        wait_for_copy_deduplicate_all
    )
    wait_for_telemetry_derived__core_clients_first_seen__v1 = (
        ExternalTaskCompletedSensor(
            task_id="wait_for_telemetry_derived__core_clients_first_seen__v1",
            external_dag_id="copy_deduplicate",
            external_task_id="telemetry_derived__core_clients_first_seen__v1",
            execution_delta=datetime.timedelta(seconds=3600),
            check_existence=True,
Exemplo n.º 8
0
        email=[
            "*****@*****.**",
            "*****@*****.**",
            "*****@*****.**",
            "*****@*****.**",
        ],
        date_partition_parameter="submission_date",
        depends_on_past=False,
        dag=dag,
    )

    wait_for_telemetry_derived__clients_last_seen__v1 = ExternalTaskCompletedSensor(
        task_id="wait_for_telemetry_derived__clients_last_seen__v1",
        external_dag_id="bqetl_main_summary",
        external_task_id="telemetry_derived__clients_last_seen__v1",
        execution_delta=datetime.timedelta(seconds=7200),
        check_existence=True,
        mode="reschedule",
        pool="DATA_ENG_EXTERNALTASKSENSOR",
    )

    search_derived__desktop_search_aggregates_by_userstate__v1.set_upstream(
        wait_for_telemetry_derived__clients_last_seen__v1)

    wait_for_search_derived__search_aggregates__v8 = ExternalTaskCompletedSensor(
        task_id="wait_for_search_derived__search_aggregates__v8",
        external_dag_id="bqetl_search",
        external_task_id="search_derived__search_aggregates__v8",
        execution_delta=datetime.timedelta(seconds=3600),
        check_existence=True,
        mode="reschedule",
        name="export_public_data_json_telemetry_derived__ssl_ratios__v1",
        arguments=["script/publish_public_data_json"] + [
            "--query_file=sql/moz-fx-data-shared-prod/telemetry_derived/ssl_ratios_v1/query.sql"
        ] + ["--destination_table=ssl_ratios${{ds_nodash}}"] +
        ["--dataset_id=telemetry_derived"] +
        ["--project_id=moz-fx-data-shared-prod"] +
        ["--parameter=submission_date:DATE:{{ds}}"],
        image=docker_image,
        dag=dag,
    )

    wait_for_mozregression_aggregates__v1 = ExternalTaskCompletedSensor(
        task_id="wait_for_mozregression_aggregates__v1",
        external_dag_id="bqetl_internal_tooling",
        external_task_id="mozregression_aggregates__v1",
        execution_delta=datetime.timedelta(seconds=3600),
        check_existence=True,
        mode="reschedule",
        failed_states=[State.FAILED, State.UPSTREAM_FAILED, State.SKIPPED],
        pool="DATA_ENG_EXTERNALTASKSENSOR",
    )

    export_public_data_json_mozregression_aggregates__v1.set_upstream(
        wait_for_mozregression_aggregates__v1)

    wait_for_telemetry_derived__ssl_ratios__v1 = ExternalTaskCompletedSensor(
        task_id="wait_for_telemetry_derived__ssl_ratios__v1",
        external_dag_id="bqetl_ssl_ratios",
        external_task_id="telemetry_derived__ssl_ratios__v1",
        execution_delta=datetime.timedelta(seconds=10800),
        check_existence=True,
        mode="reschedule",
Exemplo n.º 10
0
    )

    mozilla_vpn_derived__funnel_fxa_login_to_protected__v1.set_upstream(
        mozilla_vpn_derived__protected__v1
    )

    mozilla_vpn_derived__funnel_fxa_login_to_protected__v1.set_upstream(
        mozilla_vpn_derived__users__v1
    )

    wait_for_firefox_accounts_derived__fxa_auth_events__v1 = (
        ExternalTaskCompletedSensor(
            task_id="wait_for_firefox_accounts_derived__fxa_auth_events__v1",
            external_dag_id="bqetl_fxa_events",
            external_task_id="firefox_accounts_derived__fxa_auth_events__v1",
            execution_delta=datetime.timedelta(seconds=900),
            check_existence=True,
            mode="reschedule",
            pool="DATA_ENG_EXTERNALTASKSENSOR",
        )
    )

    mozilla_vpn_derived__login_flows__v1.set_upstream(
        wait_for_firefox_accounts_derived__fxa_auth_events__v1
    )
    wait_for_firefox_accounts_derived__fxa_content_events__v1 = (
        ExternalTaskCompletedSensor(
            task_id="wait_for_firefox_accounts_derived__fxa_content_events__v1",
            external_dag_id="bqetl_fxa_events",
            external_task_id="firefox_accounts_derived__fxa_content_events__v1",
            execution_delta=datetime.timedelta(seconds=900),
Exemplo n.º 11
0
            "*****@*****.**",
            "*****@*****.**",
            "*****@*****.**",
            "*****@*****.**",
            "*****@*****.**",
        ],
        date_partition_parameter="submission_date",
        depends_on_past=False,
        dag=dag,
    )

    wait_for_bq_main_events = ExternalTaskCompletedSensor(
        task_id="wait_for_bq_main_events",
        external_dag_id="copy_deduplicate",
        external_task_id="bq_main_events",
        execution_delta=datetime.timedelta(seconds=14400),
        check_existence=True,
        mode="reschedule",
        pool="DATA_ENG_EXTERNALTASKSENSOR",
    )

    telemetry_derived__feature_usage__v2.set_upstream(wait_for_bq_main_events)
    wait_for_copy_deduplicate_all = ExternalTaskCompletedSensor(
        task_id="wait_for_copy_deduplicate_all",
        external_dag_id="copy_deduplicate",
        external_task_id="copy_deduplicate_all",
        execution_delta=datetime.timedelta(seconds=14400),
        check_existence=True,
        mode="reschedule",
        pool="DATA_ENG_EXTERNALTASKSENSOR",
    )
Exemplo n.º 12
0
        dataset_id="telemetry_derived",
        project_id="moz-fx-data-shared-prod",
        owner="*****@*****.**",
        email=[
            "*****@*****.**", "*****@*****.**", "*****@*****.**"
        ],
        date_partition_parameter="submission_date",
        depends_on_past=False,
        dag=dag,
    )

    wait_for_bq_main_events = ExternalTaskCompletedSensor(
        task_id="wait_for_bq_main_events",
        external_dag_id="copy_deduplicate",
        external_task_id="bq_main_events",
        execution_delta=datetime.timedelta(seconds=10800),
        check_existence=True,
        mode="reschedule",
        pool="DATA_ENG_EXTERNALTASKSENSOR",
    )

    telemetry_derived__adm_engagements_daily__v1.set_upstream(
        wait_for_bq_main_events)
    wait_for_event_events = ExternalTaskCompletedSensor(
        task_id="wait_for_event_events",
        external_dag_id="copy_deduplicate",
        external_task_id="event_events",
        execution_delta=datetime.timedelta(seconds=10800),
        check_existence=True,
        mode="reschedule",
        pool="DATA_ENG_EXTERNALTASKSENSOR",